Browse Items (16481 total)
Sort by:
-
ML Use in Fraud Detection in the Financial Sector
Detecting fraud is complex, requiring analysis of vast data over time, making it resource- intensive for human investigators. This chapter explores key forms of financial fraud, including those involving corporations, banks, and insurance sectors. It provides a thorough evaluation of various machine learning techniques, such as supervised and unsupervised learning, deep learning, and ensemble methods, used to detect and prevent these financial crimes. The chapter examines the effectiveness of algorithms like LR, DT, SVM, and NN in identifying complex fraud patterns. Additionally, it discusses advanced approaches like anomaly detection, clustering, and real- time fraud detection systems. It highlights ongoing challenges and proposes potential future developments, including explainable AI, federated learning, and improved data processing techniques. This comprehensive exploration aims to deepen the understanding of machine learning's role in fraud detection and guide future research toward more effective and reliable fraud prevention strategies. 2025 by IGI Global Scientific Publishing. All rights reserved. -
Nickel-Enforced MoS2/MoTe2 Heterostructure for Energy Harvesting from Stray Magnetic Field
Harnessing magnetic noise fields for sustainable energy harvesting offers a pervasive power source for wireless devices. In this context, recently developed 2D van der Waals heterostructures have emerged as promising candidates for advancing the fundamental understanding of magnetoelectric (ME) coupling and the development of nanoscale ME devices. This work investigates thermo-magneto-electric coupling to enable MoS2/MoTe2-based heterostructures for harvesting energy from stray magnetic fields. Furthermore, introducing a nickel layer further enhances interfacial interactions under a magnetic field, and density functional theory (DFT) calculations confirm its significant influence on the ME behavior of the heterostructures. The optimized flexible heterostructure demonstrated an open-circuit voltage of ?4.5V and a power density of ?2.12mW/cm3 under an alternating current (AC) magnetic noise field of 1.33 mT. These results highlight the potential of the novel 2D-based heterostructure for harvesting stray magnetic fields and powering low-power electronic devices in self-powered wireless sensor network applications. 2026 Wiley-VCH GmbH. -
A self-powered and stretchable magnetic film for humanmachine interface applications
Developing stretchable, self-powered electronic interfaces for ambient energy harvesting is crucial for next-generation wearable electronics and humanmachine interface applications. We present a stretchable magnetoelectric composite film comprising Ni0.5Co0.5Fe2O4magnetic nanoparticles embedded in an Ecoflex matrix. The nanoparticles, synthesized via co-precipitation, exhibit a strong magnetic response, while Ecoflex ensures high stretchability and skin-mountable adaptability. The comprehensive structural, morphological, and magnetic analyses confirm the formation of a uniform and multifunctional film. The optimized device delivers a peak output voltage of ?8.3 V and a power density of 3.16 mW cm?3under ambient magnetic fields, outperforming conventional soft nanogenerators. The films demonstrate excellent durability under repeated deformation and maintain stable performance at tensile strains up to ?315%. Integration into a soft wearable platform enables real-time gesture recognition, with distinct voltage signals for finger bends and gestures under low-intensity magnetic fields. This work highlights the potential of magnetic/Ecoflex-based nanogenerators in self-powered, wearable, stretchable electronics, smart prosthetics, and intelligent humanmachine interfaces. This journal is The Royal Society of Chemistry, 2025 -
Defect-Controlled Charge-Carrier Dynamics in M- and W-Type Hexaferrites
Defect engineering provides an effective means of tuning the charge transport in ferrimagnetic oxides. Here, we present a comparative study of M-type (BaFe12O19, SrFe12O19) and W-type (BaCo2Fe16O27, BaZn2Fe16O27) hexaferrites synthesized via solgel auto-combustion. Using XRD, SEM, TEM, dielectric measurements, and currentvoltage measurements, lattice defects are linked to charge-carrier conduction pathways. XRD confirmed phase-pure hexagonal structures with nanocrystallite sizes of 3336nm. High-resolution TEM revealed edge dislocations and planar strain fields in BaFe12O19, along with stacking-fault arrays in BaCo2Fe16O27, which create localized strain-induced potential fluctuations. The presence of dislocations and oxygen-vacancy defects promotes field-assisted thermionic emission with trap densities of ?1016 cm?3 and earlier onset of space-charge-limited conduction. Dielectric spectroscopy revealed MaxwellWagner relaxation, while the JE analysis indicated that Schottky emission dominates, with secondary space-charge-limited conduction occurring at high electric fields. The results demonstrate that oxygen-vacancy and strain-related defects serve as active transport mediators, providing a pathway to tune the electrical properties of ferrites for multifunctional electronic and energy applications. 2026 The American Ceramic Society. -
Leveraging Machine Learning to Predict Revenue-Generating Sessions in E-Commerce Platforms
Due to the rapid growth of e commerce, develops effective predictive models of online shopper behavior has become important. The goal of this study is to use dataset of online shopping sessions to predict purchase intentions based on session characteristics, user behavior and site metrics. This research aims to apply machine learning and deep learning models to predict online purchasing intentions to assist businesses to improve their strategies of maximizing conversion rates. Using a dataset having numerical and categorical features, features like page views, session duration, bounce rates etc., and the presence of some special days near the user session, we used. We evaluated nine models, including the traditional methods: Logistic Regression, Decision Tree, Naive Bayes, ensemble methods: Random Forest, Gradient Boosting, XGBoost, and more advanced ones like Support Vector Machines (SVM), k-Nearest Neighbors (k-NN), and Neural Networks. Then, key metrics including Accuracy, Precision, Recall, F1 Score and ROC AUC were used to asses each model. We find that ensemble models perform best (ROC AUC = 0.9245) with Gradient Boosting performing best, with XGBoost and Random Forest close behind. With a competitive ROC AUC of 0.9000, neural networks showed strong potential, but fell slightly behind in recall compared with ensemble methods. Logistic Regression and Decision Tree were simpler models that did not achieve as strongly in predictive accuracy as more complex model; however they provided a baseline insight. Through this analysis, ensemble models and deep learning showed to be very efficient to predict online purchase intentions and provide actionable insights to optimize e-commerce platforms. 2025 IEEE. -
Social security concerns of students pursuing higher education during Russia-Ukraine conflict: Legal analysis /
A stateless migrant is not considered a citizen or national of any country under the operation of its laws. Such a person has no recognized nationality or legal status and is therefore not entitled to the protection and benefits of any state. Stateless migrants may face significant difficulties in exercising their basic human rights, including the right to education, work, and access to healthcare, among others. There are many different concepts regarding migrants and stateless migrants. This research will emphasize upon the concept of stateless migrant and the Indian students those are pursuing higher education from Ukraine and that is disturbed because of the uncertain conflict happened in Ukraine. Migrant is defined as a person who leaves their country of origin to live in another country, while a stateless migrant is someone who does not have a recognized nationality. Both concepts are important to understand when considering the rights of individuals. However, this research will also encounter often challenges in ensuring that these rights should be respected and protected by the authorities. -
Population-Environment Nexus: Interactions, Impacts, and Sustainability
Research regarding the delicate balance between population dynamics and environmental sustainability underlines ecological preservation and human growth. This essay examines the linkage between population and the environment: the global, historical, and contemporary perspectives, and policy frameworks for linking population, the environment, and policymaking. The research methodology implemented is doctoral, focusing on theories given by different demographers, for example, Malthusian warnings on population increasing more rapidly than the availability of resources are, on the contrary, contrasted by Boserup's optimism based on innovation being sustainable and similar theories. The rapid urbanization, resource consumption, and population growth are examined against the backdrop of pressing global issues like biodiversity loss, deforestation, climate change, and water scarcity. Case studies from high-income and low-income countries show how the environmental loads differ across socioeconomic spectrums. The research emphasizes on measures like family planning, sustainable development goals, and environmental governance in addressing these problems. Innovative strategies such as clean energy, sustainable agriculture, and circular economies are recognized as being essential in reducing environmental degradation and promoting inclusive growth. Intergenerational justice and resource equity are critical ethical considerations that should be considered with utmost care when developing sustainable policies. This paper draws on cross-disciplinary viewpoints and international cooperation to provide a meaningful contribution to ensuring a sustainable future for the next generation in a delicate balance between ecological conservation and population growth. 2026 John Wiley & Sons Ltd. All rights reserved. -
Deep Learning Ensemble for Neuro-Oncological Diagnostics: Fusion of VGG-16 and Convolutional Neural Network Architectures
Brain tumors are potentially fatal, prompt and accurate diagnosis is essential to appropriate treatment and management. MRI is a key method for locating tumors in the brain. This study introduces a HYBRID deep learning for binary classification of brain tumors, combining a pre trained VGG16 model with tailored CNN and Neural Networks. The fusion of these models is done via feature concatenation followed by a common classifier. This fusion helps in capturing both high-level abstract and task-specific features critical for classification. To help minimize overfitting and improve generalization, the models are subjected to rigorous data augmentation including rotation, zooming, and horizontal flipping, normalization, and resizing of images to 150 150 pixels. All models are trained and validated using the same data splits. Performance is determined by accuracy, training and validation loss, confusion matrices, and visualization with Matplotlib plots and Plotly which provide a vivid insight into the models. Experiments are conducted to determine the different model performances and the hybrid model attained an accuracy of 98.14%, which was higher than the standalone VGG16 (93%), CNN (91%), and NN (88%) models. 2025 IEEE. -
Linear Regression Tree and Homogenized Attention Recurrent Neural Network for Online Training Classification
Internet has become a vital part in people's life with the swift development of Information Technology (IT). Predominantly the customers share their opinions concerning numerous entities like, products, services on numerous platforms. These platforms comprises of valuable information concerning different types of domains ranging from commercial to political and social applications. Analysis of this immeasurable amount of data is both laborious and cumbersome to manipulate manually. In this work, a method called, Linear Regression Tree-based Homogenized Attention Recurrent Neural Network (LRT-HRNN) for online training is proposed. In the first step, a dataset consisting of student's reactions on E-learning is provided as input. A Linear Regression Decision Tree (LRT) - based feature (i.e., student's reactions and posts) selection model is applied in the second step. The feature selection model initially selects the commonly dispensed features. In the last step, HRNN sentiment analysis is employed for aggregating characterizations from prior and succeeding posts based on student's reactions for online training. During the experimentation process, LRT-HRNN method when compared with existing methods such as Attention Emotion-enhanced Convolutional Long Short Term Memory (AEC-LSTM) and Adaptive Particle Swarm Optimization based Long Short Term Memory (APSO-LSTM, performed better in terms of accuracy(increased by 6%), false positive rate (decreased by 22%), true positive rate (increased by 7%) and computational time (reduced by 21%). 2022 IEEE. -
SM-SegNet: A Lightweight Squeeze M-SegNet for Tissue Segmentation in Brain MRI Scans
In this paper, we propose a novel squeeze M-SegNet (SM-SegNet) architecture featuring a fire module to perform accurate as well as fast segmentation of the brain on magnetic resonance imaging (MRI) scans. The proposed model utilizes uniform input patches, combined-connections, long skip connections, and squeezeexpand convolutional layers from the fire module to segment brain MRI data. The proposed SM-SegNet architecture involves a multi-scale deep network on the encoder side and deep supervision on the decoder side, which uses combined-connections (skip connections and pooling indices) from the encoder to the decoder layer. The multi-scale side input layers support the deep network layers extraction of discriminative feature information, and the decoder side provides deep supervision to reduce the gradient problem. By using combined-connections, extracted features can be transferred from the encoder to the decoder resulting in recovering spatial information, which makes the model converge faster. Long skip connections were used to stabilize the gradient updates in the network. Owing to the adoption of the fire module, the proposed model was significantly faster to train and offered a more efficient memory usage with 83% fewer parameters than previously developed methods, owing to the adoption of the fire module. The proposed method was evaluated using the open-access series of imaging studies (OASIS) and the internet brain segmentation registry (IBSR) datasets. The experimental results demonstrate that the proposed SM-SegNet architecture achieves segmentation accuracies of 95% for cerebrospinal fluid, 95% for gray matter, and 96% for white matter, which outperforms the existing methods in both subjective and objective metrics in brain MRI segmentation. 2022 by the authors. Licensee MDPI, Basel, Switzerland. -
Analyzing Wholesale Trade Volume in Uzbekistan: A Data-Driven Study of Internal Trade Dynamics
Wholesale trade as a segment of internal trade possesses a great potential for shaping supply chain management, and market conditions in Uzbekistan. This paper discusses monthly changes of the wholesale trade volume regarding its main issues, seasonal fluctuations, and regional diversification using the SDMX dataset. Using timeseries analysis, trend decomposition, and correlation modeling, this paper aims at determining the effects of the economic policy, consumer demand factors, and trade restrictions in the wholesale trade sector in Uzbekistan. It also reveals seasonality in the trade, trade heterogeneity across regions, and impact of a shock in the market, which is very relevant and useful for policymakers and key players in the trade business. 2025 IEEE. -
EDSSR: a secure and power-aware opportunistic routing scheme for WSNs
Motivated by the pivotal role of routing in Wireless Sensor Networks (WSNs) and the prevalent security vulnerabilities arising from existing protocols, this research tackles the inherent challenges of securing WSNs. Many current WSN routing protocols prioritize computational efficiency but lack robust security measures, making them susceptible to exploitation by malicious actors. The prevalence of reactive protocols, chosen for their lower bandwidth consumption, exacerbates security concerns, as proactive alternatives require more resources for maintaining network routes. Additionally, the ad hoc nature and energy constraints of WSNs render conventional security models designed for wired and wireless networks unsuitable. In response to these limitations, this paper introduces the Secured Energy-Efficient Opportunistic Routing Scheme for Sustainable WSNs (EDSSR). EDSSR is designed to enhance security in WSNs by continuously updating neighbor information and validating the legitimacy of standard routing parameters. Critically, the protocol is power-aware, recognizing the vital importance of energy considerations in the constrained environment of WSNs. To assess the efficacy of EDSSR in mitigating WSN vulnerabilities, simulation experiments were conducted, evaluating the protocols performance on key metrics such as throughput, average End-to-End delay (delay), energy consumption (EC), network lifetime (alive nodes), and malware detection rate. The results demonstrate that the EDSSR protocol significantly improves performance. It shows substantial gains in sum goodput relative to throughput, average delay, EC, and alive nodes. Specifically, the EDSSR protocol is 23% faster than DLAMD and 1013% faster than EEFCR. Additionally, the malware detection rate increases by 23%. The Author(s) 2024. -
The Evolution of Interindustry Technology Linkage Topics and Its Analysis Framework in Three-Dimensional Printing Technology
The mutual influence and complementarity of technologies between different industries are becoming increasingly prominent. Revealing the topic evolution of technology linkages between industries is the foundation for understanding the technological development trend of the industry. Although numerous works have focused on technology topic mining and its evolution characteristics, these works have not accurately represented the interindustry technology linkage, analyze the related topics and even ignored the technological development characteristics hidden in the topic evolution pathway. Since the Lingo algorithm fully considers the time-series characteristics of the topics, and the knowledge evolution theory can reveal three inherent characteristics in the evolution of knowledge topics, namely, 'stability, heredity, and variability,' this article aims to combine the Lingo algorithm and the knowledge evolution theory to analyze the topic evolution of interindustry technology linkages. Additionally, because three-dimensional (3-D) printing technology has significant interdisciplinary and cross-industry characteristics, a wide range of application fields, and various interindustry technology linkages, 3-D printing technology is used for empirical analysis. The empirical results show that the key topics of interindustry technology linkages in 3-D printing include model design, manufacturing methods, manufacturing equipment, manufacturing material, and application. In addition, all these topics have the development feature of heredity. However, the topic of manufacturing materials presents significant variability, the topic of manufacturing methods has the strongest stability, and multiple subtopics of the five topics show variability and genetic intersection. 2023 IEEE. -
A POWERFUL ITERATIVE APPROACH for QUINTIC COMPLEX GINZBURG-LANDAU EQUATION within the FRAME of FRACTIONAL OPERATOR
The study of nonlinear phenomena associated with physical phenomena is a hot topic in the present era. The fundamental aim of this paper is to find the iterative solution for generalized quintic complex Ginzburg-Landau (GCGL) equation using fractional natural decomposition method (FNDM) within the frame of fractional calculus. We consider the projected equations by incorporating the Caputo fractional operator and investigate two examples for different initial values to present the efficiency and applicability of the FNDM. We presented the nature of the obtained results defined in three distinct cases and illustrated with the help of surfaces and contour plots for the particular value with respect to fractional order. Moreover, to present the accuracy and capture the nature of the obtained results, we present plots with different fractional order, and these plots show the essence of incorporating the fractional concept into the system exemplifying nonlinear complex phenomena. The present investigation confirms the efficiency and applicability of the considered method and fractional operators while analyzing phenomena in science and technology. 2021 The Author(s). -
Four Alternative Scenarios of Commons in Space: Prospects and Challenges
The rapid expansion of human activities in outer space is likely to bring new economic, social, and political dilemmas in the next 50 to 100 years. Future governance will have to increasingly juggle earth-space social justice, resource trade-offs, and environmental sustainability issues. This poses new challenges to the governance of global commons, i.e. whether existing studies are fit to address commons in a global context and whether the governance of outer space commons (dis)integrates with Earth-bound sustainability governance. To explore these questions, this study uses scenario-building techniques to generate alternative future scenarios via a workshop conducted during the 2022 Commons in Space conference. We derived four future scenarios based on two major contextual conditions: (i) the degree of equity in resource distribution in space, and (ii) the degree of integration with Earth-bound sustainability, more specifically Earth system governance. The four alternative scenarios are (i) Space Cartel in which the use of space resources becomes dominated by the rich and powerful; (ii) Earth-centric Gold Rush in which the current business as usual continues; (iii) Open Space (also Space Utopia) in which open access of space resources leads to thriving developments in space at the expense of sustainability on Earth; and finally, (iv) Earth-Space Sustainability in which challenges on Earth and in space are addressed through an integrative governance model. Based on the challenges identified from these scenarios, we discuss specific as well as cross-cutting implications for policy and governance to better address commons in space in the future. 2023 The Author(s). -
Improved tweets in English text classification by LSTM neural network
This paper analyzes the performance of an LSTM-type neural network in the sentiment analysis task in tweets in English about the COVID-19 pandemic. Primarily, the organization and cleaning a database of tweets about the COVID-19 pandemic is performed. From the original database, two other databases through different discretizations of the polarities of the tweets using Heaviside-type functions are created. Vectorization of tweets using the Word2Vec word embedding technique is carried out. Computational implementations of LSTM neural networks to the context of our research problem are adapted. Analyzes and discussions on the feasibility of the proposed solution taking into account different types of hyperparametric adjustments in the neural network models is carried out. Publicly available databases organized through the Mendeley Data public data repository are used. 2023 IEEE. -
A concise and effectual method for neutral pitch identification in stuttered speech
Researchers have studied that human-computer interactions (HCIs) can be more effective only when machines understand the emotions conveyed in speech. Speech emotion recognition has seen growing interest in research due to its usefulness in different applications. Building a neutral speech model becomes an important and challenging task as it can help in identifying different emotions from stuttered speech. This paper suggests two different approaches for identifying neutral pitch from stuttered speech. The implementation has proved through its accuracy the best model that can be adopted for neutral speech pitch identification. 2017 Walter de Gruyter GmbH, Berlin/Boston. -
Adaptive Communication Protocols for Manager-Worker Small LLM Multi-Agent Systems in Resource-Constrained Environments
The proliferation of Internet of Things (IoT) and edge computing paradigms has necessitated the deployment of intelligent multi-agent systems in resource-constrained environments, where traditional communication protocols fail to optimize bandwidth utilization and energy consumption. This paper presents a novel adaptive communication framework specifically designed for manager-worker small Large Language Models (LLMs) multi-agent systems operating under stringent computational, memory, and energy constraints. Our approach integrates three synergistic innovations: (1) a lightweight semantic filtering module employing knowledge-distilled small LLMs (DistilBERT 66M parameters, TinyBERT 4.4M parameters) for real-time extraction of task-relevant information with minimal computational overhead, (2) a dynamic hierarchical coordination scheme enabling runtime role reassignment based on evolving task complexity and resource availability, and (3) an adaptive topology control mechanism leveraging algebraic connectivity measures to optimize network robustness while minimizing communication overhead. Comprehensive simulation-based evaluation across five distinct IoT deployment scenarios demonstrates substantial improvements in communication efficiency, achieving an average token reduction of 5 7. 4 % (range: 5 4. 1 - 5 9. 4 %) while maintaining task completion rates within 8.3 percentage points of baseline performance. The framework exhibits superior coordination quality improvements of 6.0 %, coupled with significant resource optimization including 5 1. 2 % CPU usage reduction and 50.4 % energy savings, validating its practical suitability for edge computing deployments in resource-critical applications. 2025 IEEE. -
A study on branding strategies (green innovation and international marketing) and their impact on purchase decision involvement of customers in the textile industry, with disposable income as a moderating factor; [Studiu privind strategiile de branding (inova?ie ecologic? ?i marketing interna?ional) ?i impactul acestora asupra implic?rii decizia de cump?rare a clien?ilor din industria textil?, cu venitul disponibil ca factor moderator]
Branding strategies and customer involvement have become central to Indian businesses as sustainability gains prominence across both offline and online businesses. Due to rising environmental concerns, companies are focusing on sustainable practices, energy-efficient solutions, and eco-friendly products to meet consumer demands and regulatory standards. Purchasing the products based on green innovative marketing strategies has attracted people from various nations, too. However, purchasing decisions vary from one individual to another based on the driving factors like persona, psychological, economic, payment mode, social, quality, trust, cost, reputation, reviews and offers. In this research, the association between branding strategies as an independent factor using green innovation and international marketing strategies against the dependent factor, customer involvement in the textile industry, is examined. The moderating factor disposable income is adopted here, which gives this research its uniqueness, significance and novelty. The research adopts SEM analysis for examining the variables and the Hayes Process for moderating factor analysis. The targets are people who are interested in fashion clothing. The sample size used is n=589. The findings showed that there exists an association between green innovation in marketing (GIM) and purchase decision involvement (PDI) and international marketing (IM) and PDI. Similarly, the moderating factor, disposable income (DI), moderates the association between GIM and PDI; whereas it doesnt moderate the IM and PDI. Thus, the research concluded that the disposable income as a moderating factor certainly impacts the purchase decision of the customers and international marketing strategies in the fashion clothing in textile industry. 2025, Institute National Cercetare-Dezvoltare Textiles Pielarie. All rights reserved. -
Identification of Consumer Buying Patterns using KNN in E-Commerce Applications
In recent days, with the advancement of technologies, people use electronic medium to carry out their businesses. E-commerce is a process of allowing people to buy and sell products online using electronic medium. E-commerce has a wide range of customer base as well. The data generated through transaction helps the enterprises to develop the marketing strategy. The growth of this e-commerce application depends on several factors. Some of the factors are follows 1) Customer demand, 2) Analyzing buying pattern of the users, 3) Customer retention, 4) dynamic pricing etc. It is very difficult to analyze the buying pattern of customers as there is a wide range of customer base in the online platform. To overcome this problem, this research study discusses about the challenges and issues in e-commerce applications, also identifies and analyses the buying patterns of customer using various machine learning techniques. From the implementation it is identified that, KNN algorithm performed well while comparing it with various other machine learning algorithms. Performances of these algorithms have been analyzed using various matrices. For analyzing, the model is tested using e-commerce dataset (Amazon dataset downloaded from Kaggle.com). From the analysis it found that KNN algorithm computes and predicts better compared to other machine learning algorithms either Nae Bayes, or Random Forest, or Logistic Regression etc. 2023 IEEE.